检索结果-内蒙古大学图书馆

Image Denoising Using Bandelets and Hidden Markov Tree Models

Chinese Journal of Electronics 2023年第4期19卷 646-650页

作者： Wenge Zhang Suang Wang Fang Liu Xinbo Gao Licheng Jiao School of Computer Science and Technology Xidian University Xi'an China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an China

In this paper, both the marginal and joint statistics of second generation Orthogonal bandelet transform (OBT) coefficients of natural images are firstly studied, and the highly non-Gaussian marginal statistics and strong interscale, interlocation and interdirection dependencies among OBT coefficients are found. Then a Hidden Markov tree (HMT) model in OBT domain which can effectively capture all dependencies across scales, locations and directions is developed. The main contribution of this paper is that it exploits the edge direction information of OBT coefficients, and proposes an image denoising algorithm (B-HMT) based on HMT model in OBT domain. We apply B-HMT to denoise natural images which contaminated by additive Gaussian white noise, and experimental results show that B-HMT outperforms the Wavelet HMT (W-HMT) and Contourlet HMT (C-HMT) in terms of visual effect and objective evaluation criteria.

关键词： Geometry Analytical models Additives Hidden Markov models Transforms White noise Visual effects

来源：评论

学校读者我要写书评

暂无评论

A Personalized Collaborative Filtering Recommendation System of Network Document Resource Based on Knowledge Graph 3rd

A Personalized Collaborative Filtering Recommendation System...

引用

3rd International Conference on Cyberspace Data and Intelligence, Cyber DI 2019, and the International Conference on Cyber-Living, Cyber-Syndrome, and Cyber-Health, CyberLife 2019

作者： Wu, Yuezhong Chen, Rongrong Li, Changyun Chen, Shuhong College of Artificial Intelligence Hunan University of Technology Zhuzhou China Intelligent Information Perception and Processing Technology Hunan Province Key Laboratory Zhuzhou China College of Business Hunan University of Technology Zhuzhou China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China School of Computer and Communication Hunan Institute of Engineering Xiangtan China

ISBN: (纸本)9789811519215

The Internet has become one of the important channels for users to obtain information and knowledge. It is crucial that how to acquire personalized requirement of users accurately and effectively from huge amount of network document resource. This paper proposes a personalized collaborative filtering recommendation system for network document resource exploration using knowledge graph which can solve the problem of information overload and resource trek effectively. Extensive system test has been carried out in the field of big data application in packaging industry. The experimental results show that the proposed system recommends network document resource more accurately, and further improves recommendation quality using knowledge graph. Therefore, it can meet people’s personalized resource need more effectively. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Object Detection Algorithm Based on Coordinate Attention and Context Feature Enhancement 22

Object Detection Algorithm Based on Coordinate Attention and...

引用

Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition

作者： Lingzhi Liu Baohua Qiang Yuanchun Wang Xianyi Yang Jubo Tian Shihao Zhang Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC China

ISBN: (纸本)9781450397056

In recent years, object detection has been widely used in various fields such as face detection, remote sensing image detection and pedestrian detection. Due to the complex environment in the actual scene, we need to fully obtain the feature information in the image to improve the accuracy of object detection. This paper proposes an object detection algorithm based on coordinate attention and contextual feature enhancement. We design a multi-scale attention feature pyramid network, which first uses multi-branch atrous convolution to capture multi-scale context information, and then fuses the coordinate attention mechanism to embed location information into channel attention, and finally uses a bidirectional feature pyramid structure to effectively fuse high-level features and low-level features. We also adopt the GIoU loss function to further improve the accuracy of object detection. The experimental results show that the proposed method has certain advantages compared with other detection algorithms in the PASCAL VOC datasets.

关键词： Feature pyramid network Object detection Coordinate attention Atrous convolution

来源：评论

学校读者我要写书评

暂无评论

Semantic Maximum Relevance and Modal Alignment for Cross-Modal Retrieval 22

Semantic Maximum Relevance and Modal Alignment for Cross-Mod...

引用

Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition

作者： Pingping Sun Baohua Qiang Zhiguang Liu Xianyi Yang Guangyong Xi Weigang Liu Ruidong Chen Shihao Zhang Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC China

ISBN: (纸本)9781450397056

With the increasing abundance of multimedia data resources, researches on mining the relationship between different modalities to achieve refined cross-modal retrieval are gradually emerging. In this paper, we propose a novel Semantic Maximum Relevance and Modal Alignment (SMR-MA) for Cross-Modal Retrieval, which utilizes the pre-trained model with abundant image text information to extract the features of each image text, and further promotes the modal information interaction between the same semantic categories through the modal alignment module and the multi-layer perceptron with shared weights. In addition, multi-modal embedding is distributed to the normalized hypersphere, and angular edge penalty is applied between feature embedding and weight in angular space to maximize the classification boundary, thus increasing both intra-class similarity and inter-class difference. Comprehensive analysis experiments on three benchmark datasets demonstrate that the proposed method has superior performance in cross-modal retrieval tasks and is significantly superior to the state-of-the-art cross-modal retrieval methods.

关键词： Semantic Relevance CLIP Cross-Modal Retrieval Modal Alignment

来源：评论

学校读者我要写书评

暂无评论

3D Reconstruction of Indoor Scenes Using RGB-D Monocular Vision

3D Reconstruction of Indoor Scenes Using RGB-D Monocular Vis...

引用

International Conference on Robots & intelligent System (ICRIS)

作者： Sanmao Liu Wenqiu Zhu Canqing Zhang Wenjing Sun School of Computer and Communication HuNan University of Technology Zhu Zhou China Key Laboratory of Intelligent Information Perception and Processing Technology Zhuzhou Hunan Province China

ISBN: (纸本)9781509041565

Aiming at the problem of low speed of 3D reconstruction of indoor scenes with monocular vision, the color images and depth images of indoor scenes based on ASUS Xtion monocular vision sensor were used for 3D reconstruction. The image feature extraction using the ORB feature detection algorithm, and compared the efficiency of several kinds of classic feature detection algorithm in image matching, Ransac algorithm and ICP algorithm are used to point cloud fusion. Through experiments, a fast 3D reconstruction method for indoor, simple and small-scale static environment is realized. Have good accuracy, robustness, real-time and flexibility.

关键词： Cameras Three-dimensional displays Feature extraction Algorithm design and analysis Calibration Image reconstruction Mathematical model

来源：评论

学校读者我要写书评

暂无评论

A Survey of Multimodal Composite Editing and Retrieval

arXiv

引用

arXiv 2024年

作者： Li, Suyan Huang, Fuxiang Zhang, Lei The Chongqing Key Laboratory of Bio-perception and Multimodal Intelligent Information Processing Chongqing University Chongqing400044 China The Hong Kong University of Science and Technology Hong Kong The Chongqing Key Laboratory of Bio-perception and Multimodal Intelligent Information Processing the School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China

In the real world, where information is abundant and diverse across different modalities, understanding and utilizing various data types to improve retrieval systems is a key focus of research. Multimodal composite retrieval integrates diverse modalities such as text, image and audio, etc. to provide more accurate, personalized, and contextually relevant results. To facilitate a deeper understanding of this promising direction, this survey explores multimodal composite editing and retrieval in depth, covering image-text composite editing, image-text composite retrieval, and other multimodal composite retrieval. In this survey, we systematically organize the application scenarios, methods, benchmarks, experiments, and future directions. Multimodal learning is a hot topic in large model era, and have also witnessed some surveys in multimodal learning and vision-language models with transformers published in the PAMI journal. To the best of our knowledge, this survey is the first comprehensive review of the literature on multimodal composite retrieval, which is a timely complement of multimodal fusion to existing reviews. To help readers’ quickly track this field, we build the project page for this survey, which can be found at https://***/fuxianghuang1/Multimodal-Composite-Editing-and-Retrieval. © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Matching Algorithm for Legal Issues Based on BERT and Graph Convolution with Multi-granularity Features 23

Semantic Matching Algorithm for Legal Issues Based on BERT a...

引用

Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition

作者： Baohua Qiang Shijie Pang Keliang Teng Zhiguang Liu Weigang Liu Guilin University of Electronic Technology China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC China

ISBN: (纸本)9798400707988

In recent years, pre-training models represented by BERT have shown amazing text semantic representation capabilities supported by large-scale corpus, and now have become one of the mainstream solutions for semantic matching tasks in legal Q&A systems. However, pre-training models generally do not set specific pre-training tasks in terms of syntactic information, but implicitly and incidentally learn in large-scale unsupervised, which does not make good use of syntactic information as an important factor for representing semantics. To address this problem, this paper proposes a multi-granularity feature semantic matching model based on BERT and graph convolution. The model first obtains syntactic features of sentences in the form of dependent syntactic trees using existing tools, and then fuses syntactic features with word features and sentence features of BERT using an attention mechanism and graph convolutional neural network to enhance the characterization of text semantics and make the model better for semantic matching tasks. Experimental results show that the algorithm achieves significant improvements in the semantic matching task and outperforms the five comparison methods in the DIAC2019 dataset. Compared to the baseline model Sentenct-BERT, the accuracy, precision, recall and F1 values are improved by 0.33%, 1.18%, 1.03% and 1.05% improvement.

关键词： BERT Graph Convolutional Neural Network Legal Q&A Semantic matching

来源：评论

学校读者我要写书评

暂无评论

A Parallel Artificial Immune Model for Optimization

A Parallel Artificial Immune Model for Optimization

引用

International Conference on Computational Intelligence and Security

作者： Yutao Qi Fang Liu Licheng Jiao School of Computer Science And Technology Key Laboratory of Intelligent Perception and Imagee Understanding of Ministry of Education Xidian University Xi'an China Institute of Intelligent Information Processing and Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an China

This paper presents a parallel artificial immune model termed as tower master-slave model (TMSM) for solving optimising problems. Based on TMSM, the parallel immune memory clonal selection algorithm (PIMCSA) is also proposed. TMSM is a two level coarse-grained parallel artificial immune model with distributed immune response and distributed immune memory. In PIMCSA, vaccines are extracted and migrated between populations rather than individual migration as has been done in parallel genetic algorithms. It is a good balance between population diversity and the convergent speed. Experimental results on the numerical optimization and TSP problems show that PIMCSA achieves good performance in terms of both solution quality and computation time.

关键词： Immune system Genetic algorithms Artificial immune systems Competitive intelligence Master-slave Laboratories Computer science education Poles and towers Vaccines Parallel processing

来源：评论

学校读者我要写书评

暂无评论

A novel image segmentation method based on an improved bacterial foraging optimization algorithm

引用

Journal of information Hiding and Multimedia Signal processing 2017年第2期8卷 348-357页

作者： Zeng, Zhi Gao Guan, Liang Hua Zhu, Yan Hui Liu, Qiang He, Jin Rong College of Computer and Communication Hunan University of Technology ZhuzhouHunan412000 China Intelligent Information Perception and Processing Technology Hunan Province Key Laboratory China College of Information Engineering Northwest A and F University YanglingShaanxi Province712100 China

When some bionic optimization algorithms are used for image segmentation, we find that the search speeds of these algorithms are slow and the local searching abilities of these algorithms need be improved. In order to solve these problems, this paper proposed a new image segmentation method based on the improved bacterial foraging optimization algorithm. Firstly, a dynamic step size is used to instead of the fixed step size of the chemotaxis operator, and a dynamic probability is used to instead of the fixed probability of elimination-dispersal operator. Then, the gray histograms of the images are extracted for the image segmentation. Ultimately, the images are segmented using the improved bacterial foraging optimization algorithm. The image segmentation results show that the accuracy and the speed of the image segmentation based on the improved bacterial foraging optimization algorithm are superior to the ones that based on others traditional bionic optimization algorithms. © 2017 ISSN.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Automatic Summarization Generation technology of Network Document Based on Knowledge Graph 1

引用

2nd EAI International Conference on Advanced Hybrid information processing, ADHIP 2018

作者： Wu, Yuezhong Chen, Rongrong Li, Changyun Chen, Shuhong Zou, Wenjun College of Artificial Intelligence Hunan University of Technology Zhuzhou412007 China Intelligent Information Perception and Processing Technology Hunan Province Key Laboratory Zhuzhou412007 China College of Business Hunan University of Technology Zhuzhou412007 China School of Computer Science and Educational Software Guangzhou University Guangzhou510006 China School of Computer and Communication Hunan Institute of Engineering Xiangtan411104 China

ISBN: (数字)9783030190866

ISBN: (纸本)9783030190859

The Internet has become one of the important channels for users to access to information and knowledge. It is crucial that how to acquire key content accurately and effectively in the events from huge amount of network information. This paper proposes an algorithm for automatic generation of network document summaries based on knowledge graph and TextRank algorithm which can solve the problem of information overload and resource trek effectively. We run the system in the field of big data application in packaging engineering. The experimental results show that the proposed method KG-TextRank extracts network document summaries more accurately, and automatically generates more readable and coherent natural language text. Therefore, it can help people access information and knowledge more effectively. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：